© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42903
    Prev
    Next
    INDEX
    Explanations

    ico

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ico
    -2.02
    icos
    -1.54
    ICO
    -1.44
    ica
    -1.37
    ici
    -1.27
    icus
    -1.27
    icas
    -1.25
    icae
    -1.15
    icum
    -1.10
    ICOS
    -1.00
    POSITIVE LOGITS
     zelve
    0.93
     itſelf
    0.90
     Administrativna
    0.85
     дописавши
    0.82
     незавершена
    0.80
    yntaxException
    0.79
     myſelf
    0.79
     Roskov
    0.79
     beginnetje
    0.79
     meille
    0.77
    Activations Density 0.209%

    No Known Activations